AUTOMATIC BRIGHTNESS AND CONTRAST CONTROL NEURAL NETWORK FOR MEDICAL DIAGNOSITIC IMAGING

摘要

This invention relates to estimating the window width and window level (center) which are typically used to view and then transform diagnostic imaging data to grayscale images. These grayscale images are then used to check the presence of diseases or abnormalities. For each individual diagnostic image, this invention automatically estimates the most appropriate values. This automatic estimation is done by a specialized module added on to a convolutional neural network-based disease detection system.